Improved Worst-Case Regret Bounds for Randomized Least-Squares Value Iteration

Keyphrases

• Value Iteration 100%
• Regret Bounds 100%
• Worst-case Regret 100%
• Randomized Least Squares 100%
• Least Square Value 100%
• Thompson Sampling 50%
• Sampling Methods 25%
• High Probability 25%
• Value Function 25%
• Existing State 25%
• Markov Decision Process 25%
• Reinforcement Learning 25%
• Regret Minimization 25%

Computer Science

• Least Squares Method 100%
• Function Value 33%
• Randomized Algorithm 33%
• Markov Decision Process 33%
• Reinforcement Learning 33%